In the problem sets, we use the library introduced in the first lecture (github.com/yuanchenyang...) to train diffusion models on custom data, as well as using pretrained models as building blocks for a variety of downstream tasks (see examples above).
(4/4)

Using score distillation for 3D shape generation (L5) and wrapping up with a summary of the latest research making diffusion models better and faster (L6)

The lecture recordings can be found here: www.youtube.com/playlist?lis...

(3/4)

We then talked about different theoretical perspectives and derivations of diffusion (L2), how guidance and conditioning works (L3), the puzzling question of how and why diffusion models generalize (L4), ...

(2/4)

Last month I co-taught a class on diffusion models at MIT during the IAP term: www.practical-diffusion.org

In the lectures, we first introduced diffusion models from a practitioner's perspective, showing how to build a simple but powerful implementation from the ground up (L1).

(1/4)